Skip to main content
NewSeedance 2.5 is live→
ModelRunner
bytedance avatar

Seedream V4.5 Text to Image API

bytedance/seedream-v4.5/text-to-image

A next-generation text-to-image model by ByteDance, capable of high-fidelity generation, precise text rendering, and complex stylistic control for highly detailed visual compositions.

0.04
OpenAPI

Model Input

Input

The text prompt used to generate the image

The size of the generated image. Use a preset string (e.g. '4_3_1k') or a custom {width, height} object.

Safety checker can only be disabled on API call

Min: 1 - Max: 4

The number of images to generate. Each generated image is billed.

Random seed to control the stochasticity of image generation.

You need to be logged in to run this model and view results.
Log in

Model Output

Output

Generated image output
Generated in 20.307 seconds
Logs (1 lines)

Model Example Requests

Examples

Example output 1Example output 2Example output 3

Seedream V4.5 Text to Image API

Seedream V4.5 Text to Image is a text-to-image AI model by bytedance. On ModelRunner it runs through a REST API or via MCP from any AI assistant, at $0.04 per image.

POST https://queue.modelrunner.run/bytedance/seedream-v4.5/text-to-image

cURL

# Submit a request to the queue. Input fields go at the top level of the
# body. The optional reserved "metadata" object holds your own flat string
# tags — stored on the request, never sent to the model; filter later with
# GET https://queue.modelrunner.run/requests?metadata=<url-encoded JSON>.
curl -X POST https://queue.modelrunner.run/bytedance/seedream-v4.5/text-to-image \
  -H "Authorization: Key $MRUN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "seed": 458102,
    "prompt": "A wide-angle landscape photograph of a bustling 1920s-style street corner on a rainy evening. The wet cobblestones re…",
    "image_size": "landscape_16_9",
    "max_images": 1,
    "num_images": 1,
    "enable_safety_checker": true,
    "metadata": {
      "project": "my-project"
    }
  }'
# → { "request_id": "...", "status_url": "...", "response_url": "..." }

# Poll status_url until "COMPLETED", then fetch the result
curl "https://queue.modelrunner.run/bytedance/seedream-v4.5/text-to-image/requests/$REQUEST_ID/status" \
  -H "Authorization: Key $MRUN_API_KEY"
curl "https://queue.modelrunner.run/bytedance/seedream-v4.5/text-to-image/requests/$REQUEST_ID" \
  -H "Authorization: Key $MRUN_API_KEY"

JavaScript

import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("bytedance/seedream-v4.5/text-to-image", {
  input: {
    "seed": 458102,
    "prompt": "A wide-angle landscape photograph of a bustling 1920s-style street corner on a rainy evening. The wet cobblestones re…",
    "image_size": "landscape_16_9",
    "max_images": 1,
    "num_images": 1,
    "enable_safety_checker": true
  },
});
console.log(result);

Python

import os
import requests

headers = {"Authorization": f"Key {os.environ['MRUN_API_KEY']}"}

submitted = requests.post(
    "https://queue.modelrunner.run/bytedance/seedream-v4.5/text-to-image",
    headers=headers,
    json={
      "seed": 458102,
      "prompt": "A wide-angle landscape photograph of a bustling 1920s-style street corner on a rainy evening. The wet cobblestones re…",
      "image_size": "landscape_16_9",
      "max_images": 1,
      "num_images": 1,
      "enable_safety_checker": true
    },
).json()

# Poll submitted["status_url"] until "COMPLETED", then:
result = requests.get(submitted["response_url"], headers=headers).json()

Input parameters

NameTypeRequiredDescription
promptstringyesThe text prompt used to generate the image
image_sizeenumnoThe size of the generated image. Use a preset string (e.g. '4_3_1k') or a custom {width, height} object. Default: "4_3_1k".
enable_safety_checkerbooleannoIf set to true, the safety checker will be enabled. This setting can only be configured via the API. Default: true.
num_imagesintegernoThe number of images to generate. Each generated image is billed. Default: 1.
seedintegernoRandom seed to control the stochasticity of image generation.

Machine-readable: OpenAPI schema · llms.txt

Use Seedream V4.5 Text to Image from Claude & Cursor (MCP)

Point Claude Code, Claude Desktop, Cursor, or any MCP client at the ModelRunner MCP server and Seedream V4.5 Text to Image becomes a tool your assistant can call directly — it authorizes via OAuth (no API key in config) and runs this model with the run_model tool using the endpoint bytedance/seedream-v4.5/text-to-image.

MCP client config (Claude Desktop, Cursor)

{
  "mcpServers": {
    "modelrunner": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://mcp.modelrunner.run/mcp"]
    }
  }
}

Claude Code

claude mcp add --transport http modelrunner https://mcp.modelrunner.run/mcp

Then ask your assistant, for example: “Run bytedance/seedream-v4.5/text-to-image on ModelRunner to generate image”. MCP setup guide.

Model Details

Model Details

Seedream 4.5 is a state-of-the-art text-to-image model developed by ByteDance, designed to generate stunning, high-fidelity visuals from descriptive text prompts. Built on an advanced, unified architecture, it excels at understanding complex instructions, enabling creators to craft detailed scenes, unique visual styles, and precise compositions effortlessly.

You can run this model directly via the application UI. Simply enter your descriptive prompt, choose your desired output size, and securely download your generated images using the built-in interface components.

**Features** * **Precise Text Rendering:** Reliably generates legible, clearly visible typography directly within your images based on specific prompt instructions. * **Stylistic Versatility:** Seamlessly adapts to distinct photographic styles, specific camera angles (such as selfies or wide shots), and nuanced post-processing effects (like motion blur or overexposure). * **High-Resolution Output:** Capable of generating vibrant, detailed images in various dimensions, supporting automated 2K and 4K optimizations for pristine quality.

**What it’s good at** * Creating highly stylized, photorealistic, or imaginative artistic imagery with intricate details. * Following complex, multi-layered prompts that combine specific character traits, dynamic environmental settings, and text placements simultaneously. * Generating dynamic scenes that require highly specific framing, lighting, or unique visual treatments.

**Tips** * Be as descriptive as possible. Specify the lighting, camera angles, emotional tone, and subject focus to guide the model accurately. * When adding text to your generation, explicitly place the exact phrase in quotation marks within your prompt and describe its placement and typography (e.g., *The text "Hello World" written in crisp lettering at the top*). * Use the app's UI to experiment with different detailed descriptions, and easily download multiple variations to find the perfect composition.

To run via ModelRunner JavaScript client: ```javascript import { modelrunner } from "@modelrunner/client";

const result = await modelrunner.subscribe("bytedance/seedream-v4.5/text-to-image", { input: { prompt: "A selfie of a happy cat at twilight near the Eiffel Tower, holding a piece of baklava. The photo has slight motion blur and is slightly overexposed. The text \"Seedream 4.5\" is clearly written at the top.", image_size: "auto_2K" }, });

console.log(result); ```